Yanagawa Masahiro, Nagatani Yukihiro, Hata Akinori, Sumikawa Hiromitsu, Moriya Hiroshi, Iwano Shingo, Tsuchiya Nanae, Iwasawa Tae, Ohno Yoshiharu, Tomiyama Noriyuki
Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, The University of Osaka, 2-2 Yamadaoka, Suita-city, Osaka, 565-0871, Japan.
Department of Radiology, Shiga University of Medical Science, Seta Tsukinowa-cho, Otsu, Shiga, 520-2192, Japan.
Jpn J Radiol. 2025 Jul 31. doi: 10.1007/s11604-025-01839-w.
To construct two machine learning radiomics (MLR) for invasive adenocarcinoma (IVA) prediction using normal-spatial-resolution (NSR) and high-spatial-resolution (HSR) training cohorts, and to validate models (model-NSR and -HSR) in another test cohort while comparing independent radiologists' (R1, R2) performance with and without model-HSR.
In this retrospective multicenter study, all CT images were reconstructed using NSR data (512 matrix, 0.5-mm thickness) and HSR data (2048 matrix, 0.25-mm thickness). Nodules were divided into training (n = 61 non-IVA, n = 165 IVA) and test sets (n = 36 non-IVA, n = 203 IVA). Two MLR models were developed with 18 significant factors for the NSR model and 19 significant factors for the HSR model from 172 radiomics features using random forest. Area under the receiver operator characteristic curves (AUC) was analyzed using DeLong's test in the test set. Accuracy (acc), sensitivity (sen), and specificity (spc) of R1 and R2 with and without model-HSR were compared using McNemar test.
437 patients (70 ± 9 years, 203 men) had 465 nodules (n = 368, IVA). Model-HSR AUCs were significantly higher than model-NSR in training (0.839 vs. 0.723) and test sets (0.863 vs. 0.718) (p < 0.05). R1's acc (87.2%) and sen (93.1%) with model-HSR were significantly higher than without (77.0% and 79.3%) (p < 0.0001). R2's acc (83.7%) and sen (86.7%) with model-HSR might be equal or higher than without (83.7% and 85.7%, respectively), but not significant (p > 0.50). Spc of R1 (52.8%) and R2 (66.7%) with model-HSR might be lower than without (63.9% and 72.2%, respectively), but not significant (p > 0.21).
HSR-based MLR model significantly increased IVA diagnostic performance compared to NSR, supporting radiologists without compromising accuracy and sensitivity. However, this benefit came at the cost of reduced specificity, potentially increasing false positives, which may lead to unnecessary examinations or overtreatment in clinical settings.
使用正常空间分辨率（NSR）和高空间分辨率（HSR）训练队列构建两个用于浸润性腺癌（IVA）预测的机器学习放射组学（MLR）模型，并在另一个测试队列中验证模型（模型NSR和-HSR），同时比较独立放射科医生（R1、R2）在有和没有模型-HSR情况下的表现。
在这项回顾性多中心研究中，所有CT图像均使用NSR数据（512矩阵，0.5毫米厚度）和HSR数据（2048矩阵，0.25毫米厚度）进行重建。结节被分为训练集（n = 61个非IVA，n = 165个IVA）和测试集（n = 36个非IVA，n = 203个IVA）。使用随机森林从172个放射组学特征中为NSR模型开发了具有18个显著因素的两个MLR模型，为HSR模型开发了具有19个显著因素的模型。在测试集中使用德龙检验分析受试者操作特征曲线（AUC）下的面积。使用McNemar检验比较有和没有模型-HSR时R1和R2的准确性（acc）、敏感性（sen）和特异性（spc）。
437例患者（70±9岁，203名男性）有465个结节（n = 368个，IVA）。在训练集（0.839对0.723）和测试集（0.863对0.718）中，模型-HSR的AUC显著高于模型-NSR（p < 0.05）。有模型-HSR时R1的acc（87.2%）和sen（93.1%）显著高于没有模型时（77.0%和79.3%）（p < 0.0001）。有模型-HSR时R2的acc（83.7%）和sen（86.7%）可能等于或高于没有模型时（分别为83.7%和85.7%），但差异不显著（p > 0.50）。有模型-HSR时R1的spc（52.8%）和R2的spc（66.7%）可能低于没有模型时（分别为63.9%和72.2%），但差异不显著（p > 0.21）。
与NSR相比，基于HSR的MLR模型显著提高了IVA的诊断性能，在不影响准确性和敏感性的情况下为放射科医生提供了支持。然而，这种益处是以特异性降低为代价的，可能会增加假阳性，这可能导致临床环境中不必要的检查或过度治疗。
